English
Related papers

Related papers: Auditing Black-box Models for Indirect Influence

200 papers

Motivated by the need to audit complex and black box models, there has been extensive research on quantifying how data features influence model predictions. Feature influence can be direct (a direct influence on model outcomes) and indirect…

How can we explain the predictions of a black-box model? In this paper, we use influence functions -- a classic technique from robust statistics -- to trace a model's prediction through the learning algorithm and back to its training data,…

Machine Learning · Statistics 2021-01-01 Pang Wei Koh , Percy Liang

With the increasing adoption of predictive models trained using machine learning across a wide range of high-stakes applications, e.g., health care, security, criminal justice, finance, and education, there is a growing need for effective…

Machine Learning · Computer Science 2020-08-04 Aria Khademi , Vasant Honavar

In recent years, the use of sophisticated statistical models that influence decisions in domains of high societal relevance is on the rise. Although these models can often bring substantial improvements in the accuracy and efficiency of…

Machine Learning · Computer Science 2021-04-13 Alfredo Carrillo , Luis F. Cantú , Alejandro Noriega

Predictive models are increasingly deployed for the purpose of determining access to services such as credit, insurance, and employment. Despite potential gains in productivity and efficiency, several potential problems have yet to be…

Machine Learning · Computer Science 2016-11-16 Julius Adebayo , Lalana Kagal

Many modern software systems are highly configurable, allowing the user to tune them for performance and more. Current performance modeling approaches aim at finding performance-optimal configurations by building performance models in a…

Software Engineering · Computer Science 2021-02-15 Max Weber , Sven Apel , Norbert Siegmund

In science and medicine, model interpretations may be reported as discoveries of natural phenomena or used to guide patient treatments. In such high-stakes tasks, false discoveries may lead investigators astray. These applications would…

Machine Learning · Statistics 2020-08-18 Collin Burns , Jesse Thomason , Wesley Tansey

When a model informs decisions about people, distribution shifts can create undue disparities. However, it is hard for external entities to check for distribution shift, as the model and its training set are often proprietary. In this…

Machine Learning · Computer Science 2022-09-09 Marc Juarez , Samuel Yeom , Matt Fredrikson

Understanding how changes in explanatory features affect the unconditional distribution of the outcome is important in many applications. However, existing black-box predictive models are not readily suited for analyzing such questions. In…

Machine Learning · Statistics 2024-12-10 Jing Zhou , Chunlin Li

As machine learning systems become more ubiquitous, methods for understanding and interpreting these models become increasingly important. In particular, practitioners are often interested both in what features the model relies on and how…

Machine Learning · Computer Science 2021-09-08 Andrew Yeh , Anhthy Ngo

With machine learning models being increasingly used to aid decision making even in high-stakes domains, there has been a growing interest in developing interpretable models. Although many supposedly interpretable models have been proposed,…

Artificial Intelligence · Computer Science 2021-08-17 Forough Poursabzi-Sangdeh , Daniel G. Goldstein , Jake M. Hofman , Jennifer Wortman Vaughan , Hanna Wallach

Performance-influence models can help stakeholders understand how and where configuration options and their interactions influence the performance of a system. With this understanding, stakeholders can debug performance behavior and make…

Software Engineering · Computer Science 2021-01-15 Miguel Velez , Pooyan Jamshidi , Norbert Siegmund , Sven Apel , Christian Kästner

Algorithmic audits are essential tools for examining systems for properties required by regulators or desired by operators. Current audits of large language models (LLMs) primarily rely on black-box evaluations that assess model behavior…

Computers and Society · Computer Science 2026-05-19 Hannah Cyberey , Yangfeng Ji , David Evans

Before deploying a black-box model in high-stakes problems, it is important to evaluate the model's performance on sensitive subpopulations. For example, in a recidivism prediction task, we may wish to identify demographic groups for which…

Methodology · Statistics 2023-06-09 John J. Cherian , Emmanuel J. Candès

Among the most critical limitations of deep learning NLP models are their lack of interpretability, and their reliance on spurious correlations. Prior work proposed various approaches to interpreting the black-box models to unveil the…

Computation and Language · Computer Science 2021-10-08 Xiaochuang Han , Yulia Tsvetkov

Influence functions (IFs) elucidate how training data changes model behavior. However, the increasing size and non-convexity in large-scale models make IFs inaccurate. We suspect that the fragility comes from the first-order approximation…

Machine Learning · Computer Science 2024-05-07 Hyeonsu Lyu , Jonggyu Jang , Sehyun Ryu , Hyun Jong Yang

Models can expose sensitive information about their training data. In an attribute inference attack, an adversary has partial knowledge of some training records and access to a model trained on those records, and infers the unknown values…

Cryptography and Security · Computer Science 2022-09-07 Bargav Jayaraman , David Evans

Deep learning algorithms have recently shown to be a successful tool in estimating parameters of statistical models for which simulation is easy, but likelihood computation is challenging. But the success of these approaches depends on…

Machine Learning · Statistics 2024-02-20 Amanda Lenzi , Haavard Rue

Large-scale black-box models have become ubiquitous across numerous applications. Understanding the influence of individual training data sources on predictions made by these models is crucial for improving their trustworthiness. Current…

Machine Learning · Computer Science 2024-06-21 Myeongseob Ko , Feiyang Kang , Weiyan Shi , Ming Jin , Zhou Yu , Ruoxi Jia

Complex black-box predictive models may have high performance, but lack of interpretability causes problems like lack of trust, lack of stability, sensitivity to concept drift. On the other hand, achieving satisfactory accuracy of…

Machine Learning · Computer Science 2020-02-12 Alicja Gosiewska , Przemyslaw Biecek
‹ Prev 1 2 3 10 Next ›